{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/embedding-structure-matters-comparing-methods","title":"Embedding structure matters: Comparing methods to adapt multilingual vocabularies to new languages","arxiv_id":"2309.04679","date":"2023-09-09","proceeding":null,"authors":["C. M. Downey","Terra Blevins","Nora Goldfine","Shane Steinert-Threlkeld"],"abstract":"Pre-trained multilingual language models underpin a large portion of modern NLP tools outside of English. A strong baseline for specializing these models for specific languages is Language-Adaptive Pre-Training (LAPT). However, retaining a large cross-lingual vocabulary and embedding matrix comes at considerable excess computational cost during adaptation. In this study, we propose several simple techniques to replace a cross-lingual vocabulary with a compact, language-specific one. Namely, we address strategies for re-initializing the token embedding matrix after vocabulary specialization. We then provide a systematic experimental comparison of our techniques, in addition to the recently-proposed Focus method. We demonstrate that: 1) Embedding-replacement techniques in the monolingual transfer literature are inadequate for adapting multilingual models. 2) Replacing cross-lingual vocabularies with smaller specialized ones provides an efficient method to improve performance in low-resource languages. 3) Simple embedding re-initialization techniques based on script-wise sub-distributions rival techniques such as Focus, which rely on similarity scores obtained from an auxiliary model.","url_abs":"https://arxiv.org/abs/2309.04679v2","url_pdf":"https://arxiv.org/pdf/2309.04679v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"embedding-structure-matters-comparing-methods","repo_url":"https://github.com/cmdowney88/embeddingstructure","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2309.04679","atlas_url":"https://app.syntology.ai/?focus=2309.04679","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.04679"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cmdowney88/embeddingstructure","reach":null}],"summary":{"ran_honours":1,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"74b4020b7c03984e","entry":"hex2dec","repo":"cmdowney88/embeddingstructure","repo_kind":"official","path":"src/reinitialize_embeddings.py","file_url":"https://github.com/cmdowney88/embeddingstructure/blob/HEAD/src/reinitialize_embeddings.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"74b4020b7c03984e"}},{"code_sha256_prefix":"8e6d49aaf98611d9","entry":"top_script","repo":"cmdowney88/embeddingstructure","repo_kind":"official","path":"src/reinitialize_embeddings.py","file_url":"https://github.com/cmdowney88/embeddingstructure/blob/HEAD/src/reinitialize_embeddings.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8e6d49aaf98611d9"}},{"code_sha256_prefix":"e8e4a9db7236b331","entry":"get_ord2script","repo":"cmdowney88/embeddingstructure","repo_kind":"official","path":"src/reinitialize_embeddings.py","file_url":"https://github.com/cmdowney88/embeddingstructure/blob/HEAD/src/reinitialize_embeddings.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e8e4a9db7236b331"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}